mirror of
https://github.com/RPCSX/llvm.git
synced 2026-01-31 01:05:23 +01:00
d019e8638a
This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@292982 91177308-0d34-0410-b5e6-96231b3b80d8
48 lines
2.2 KiB
LLVM
48 lines
2.2 KiB
LLVM
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
|
|
declare double @llvm.fma.f64(double, double, double) nounwind readnone
|
|
declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>) nounwind readnone
|
|
declare <4 x double> @llvm.fma.v4f64(<4 x double>, <4 x double>, <4 x double>) nounwind readnone
|
|
|
|
|
|
; FUNC-LABEL: {{^}}fma_f64:
|
|
; SI: v_fma_f64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\]}}
|
|
define void @fma_f64(double addrspace(1)* %out, double addrspace(1)* %in1,
|
|
double addrspace(1)* %in2, double addrspace(1)* %in3) {
|
|
%r0 = load double, double addrspace(1)* %in1
|
|
%r1 = load double, double addrspace(1)* %in2
|
|
%r2 = load double, double addrspace(1)* %in3
|
|
%r3 = tail call double @llvm.fma.f64(double %r0, double %r1, double %r2)
|
|
store double %r3, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fma_v2f64:
|
|
; SI: v_fma_f64
|
|
; SI: v_fma_f64
|
|
define void @fma_v2f64(<2 x double> addrspace(1)* %out, <2 x double> addrspace(1)* %in1,
|
|
<2 x double> addrspace(1)* %in2, <2 x double> addrspace(1)* %in3) {
|
|
%r0 = load <2 x double>, <2 x double> addrspace(1)* %in1
|
|
%r1 = load <2 x double>, <2 x double> addrspace(1)* %in2
|
|
%r2 = load <2 x double>, <2 x double> addrspace(1)* %in3
|
|
%r3 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %r0, <2 x double> %r1, <2 x double> %r2)
|
|
store <2 x double> %r3, <2 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fma_v4f64:
|
|
; SI: v_fma_f64
|
|
; SI: v_fma_f64
|
|
; SI: v_fma_f64
|
|
; SI: v_fma_f64
|
|
define void @fma_v4f64(<4 x double> addrspace(1)* %out, <4 x double> addrspace(1)* %in1,
|
|
<4 x double> addrspace(1)* %in2, <4 x double> addrspace(1)* %in3) {
|
|
%r0 = load <4 x double>, <4 x double> addrspace(1)* %in1
|
|
%r1 = load <4 x double>, <4 x double> addrspace(1)* %in2
|
|
%r2 = load <4 x double>, <4 x double> addrspace(1)* %in3
|
|
%r3 = tail call <4 x double> @llvm.fma.v4f64(<4 x double> %r0, <4 x double> %r1, <4 x double> %r2)
|
|
store <4 x double> %r3, <4 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|